Training in progress, step 9636

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7d9179be7efa3d039286efbd45485bca053994cd099d18d9332ecc07e690565
+oid sha256:6432e5d4dbcf96f5f64c6469ce31b0d5b3c9f01110150b82ee9cdadc1010e989
 size 667849236

runs/May05_22-15-18_ip-10-192-11-107/events.out.tfevents.1746483320.ip-10-192-11-107.1742.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fa1b1793cd7a32a78d0adb81f839c2d36b48f7ef40f2b34aab870ba9924d01c
-size 7241
+oid sha256:acc24c92646c4300934b8e42a0af0a9a570793e89cf4cb7a4bf4d6430ecf6297
+size 8333

trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 8030,
-  "best_metric": 0.7079419812877328,
-  "best_model_checkpoint": "checkpoints/checkpoint-8030",
-  "epoch": 1.2499902712378876,
+  "best_global_step": 9636,
+  "best_metric": 0.7073388677263619,
+  "best_model_checkpoint": "checkpoints/checkpoint-9636",
+  "epoch": 1.4999805424757753,
   "eval_steps": 1606,
-  "global_step": 8030,
+  "global_step": 9636,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -180,6 +180,39 @@
       "eval_steps_per_second": 1.728,
       "eval_wer": 0.6757794831111406,
       "step": 8030
+    },
+    {
+      "epoch": 1.32315056232245,
+      "grad_norm": 0.035194575786590576,
+      "learning_rate": 4.8583398752382485e-05,
+      "loss": 0.0539,
+      "step": 8500
+    },
+    {
+      "epoch": 1.4009806592209206,
+      "grad_norm": 0.03347332403063774,
+      "learning_rate": 4.782967662255196e-05,
+      "loss": 0.0523,
+      "step": 9000
+    },
+    {
+      "epoch": 1.4788107561193913,
+      "grad_norm": 0.06645191460847855,
+      "learning_rate": 4.692437323847159e-05,
+      "loss": 0.0507,
+      "step": 9500
+    },
+    {
+      "epoch": 1.4999805424757753,
+      "eval_avg": 0.7073388677263619,
+      "eval_cer": 0.6541002942380697,
+      "eval_der": 0.7938397323961762,
+      "eval_loss": 0.03928952291607857,
+      "eval_runtime": 307.3123,
+      "eval_samples_per_second": 441.645,
+      "eval_steps_per_second": 1.728,
+      "eval_wer": 0.6740765765448399,
+      "step": 9636
     }
   ],
   "logging_steps": 500,
@@ -199,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.267309210678067e+17,
+  "total_flos": 7.52077105281368e+17,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null